Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to emphasizing agreement or addition in statements

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions and phrases connecting ideas in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Riders
    -0.72
    elsen
    -0.66
    wings
    -0.65
     Survivors
    -0.63
     Commissioners
    -0.62
    sterdam
    -0.62
     flats
    -0.61
     Ll
    -0.61
    bryce
    -0.60
     Scroll
    -0.60
    POSITIVE LOGITS
    enge
    0.84
    insk
    0.76
    enged
    0.75
     sidx
    0.72
    ented
    0.71
    aucas
    0.70
    izont
    0.70
    ifiable
    0.70
    riched
    0.70
    enced
    0.70
    Act Density 0.253%

    No Known Activations